Investigating users' eye movement behavior in critiquing-based recommender systems

Recommender systems have increasingly become popular in various web environments (such as e-commerce and social media) for automatically generating items that match to individual users' personal interests. Among different types of recommender systems that have been developed so far, critiquing-based recommender systems have been widely recognized as an effective approach to obtaining users' feedback on the system's generated recommendations. Such systems have been demonstrated particularly helpful for serving new users. That is, by means of eliciting and refining their preferences through real-item feedback, the system is able to gradually improve its recommendation accuracy and aid users to make better decision. However, how to precisely acquire users' critiquing feedback is still a challenging issue. Most of existing systems rely on users to specify the feedback on their own, which unavoidably let users consume extra efforts. In our work, we have been engaged in analyzing users' eye-movement behavior when they evaluate recommendations, with the objective of identifying the correlation between eye movements and their critiquing feedback. The results can hence be constructive for developing an eye-based feedback elicitation method, so as to reduce users' self-critiquing efforts. Based on a collection of real users' eye-gaze data, we have tested this idea's feasibility. Moreover, we have compared different recommendation interfaces (the interface that displays a set of recommended products), and found the category layout performs better than the list structure in terms of stimulating users to view recommended products. As a result, multiple design guidelines are derived from our user experiment.

A Low Power Super-Regenerative Impulse Radio Ultra-Wideband Receiver in CMOS Technology

Communication systems have played a key role in changing our lives as such systems help to access remote data and to transfer it to the end user when requested. Intelligent nodes, which can process and transmit information placed in a given environment can provide localized data that might not be available through a public network such as the internet. As an example, nodes can provide dynamic data such as room temperature, chemical composition of air, or light intensity level. With the progress made in the semiconductor industry, such nodes have become compact, thereby making it easier to setup a cluster in a confined place. Often these nodes are to be placed in a remote location and hence the use of a cable to power up these devices might not be possible. Also, the use of cables makes the system bulky and heavy. For this reason battery-powered wireless sensor nodes are desirable. Such battery operated devices need to be energy efficient to avoid replacing the batteries often. Energy efficiency can be achieved by optimizing several parameters from the top (system level architecture) to the bottom (transistor level design). The thesis describes a receiver system design for Impulse-radio Ultra-Wideband (IR-UWB) signalling standard proposed in IEEE 802.11.4a for short range, low data rate communication system. The advantages of the IR-UWB signalling scheme over other existing standards and a comparison between various receiver architectures for IR-UWB standard using energy consumption as a metric is described. The main power consuming block in an IR-UWB receiver is identified to be the front-end amplifier structure as it needs to provide sufficient gain for proper operation of the subsequent stages. To reduce the power consumption of this amplifier, the super-regenerative architecture for IR-UWB system is proposed. It is shown in this work that since the super-regenerative receiver uses an amplifier with positive feedback, it can achieve high gain with a relatively low current, hence it can significantly reduce the power consumption. The super-regenerative receiver for the IR-UWB system is implemented in a 0.18 µm CMOS technology operating at 1.5 V, and the receiver energy consumption is 0.24 nJ/bit at a data rate of 10 Mbps. The receiver achieves a measured sensitivity of -66 and -61 dBm at 3.494 and 3.993 GHz, respectively, with a BER of 10-3. Finally, an automatic tuning circuitry based on a digital phase-locked loop architecture (DPLL) for super-regenerative receiver is proposed. The objective is to tune the receiver to either one of the sub-bands (3.494 or 3.993 GHz) as proposed in the IEEE 802.15.4a standard. Including the tuning circuitry helps to improve the receiver sensitivity, and also demonstrates the possibility for multi-band reception using such an architecture. The proposed DPLL is implemented in a 0.18 µm CMOS technology consuming 9.3 mW.

EPFL2010

A Low Power Super-Regenerative Impulse Radio Ultra-Wideband Receiver in CMOS Technology

EPFL2010